论文部分内容阅读
针对非平衡产品制造数据关键质量特性(critical to quality characteristics,CTQs)识别,提出基于NSGA-Ⅱ的特征选择算法.首先,在分类错误率和特征子集大小基础上,针对数据非平衡性,引入第Ⅱ类错误率度量质量特性子集的重要性.接着,应用多目标进化算法NSGA-Ⅱ最小化以上三个度量标准,得到非支配解集.最后,引入理想点法从非支配解集中选择最佳调和解,得到CTQ集.算例结果表明,所提算法能够得到较高分类精度,同时有效降低第Ⅱ类错误率与CTQ集大小,说明了算法的有效性.
Aiming at the identification of critical to quality characteristics (CTQs) of non-equilibrium product manufacturing data, a feature selection algorithm based on NSGA-Ⅱ is proposed.Firstly, based on the classification error rate and feature subset size, aiming at data unbalance, The second class error rate measures the importance of the subsets of quality characteristics.Secondly, we apply the multi-objective evolutionary algorithm NSGA-Ⅱ to minimize the above three metrics to get the nondominated solution set.Finally, we introduce the ideal point method to choose from the nondominated solution set The optimal reconciliation solution is obtained, and the set of CTQs is obtained.Experimental results show that the proposed algorithm can achieve higher classification accuracy and reduce the class Ⅱ error rate and CTQ set size effectively, which shows the effectiveness of the algorithm.